© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37963
    Prev
    Next
    INDEX
    Explanations

    bus stop

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    د
    0.77
    erne
    0.70
    eres
    0.68
    aft
    0.68
     {
    0.65
    app
    0.64
    att
    0.63
    ac
    0.61
    have
    0.61
    affection
    0.61
    POSITIVE LOGITS
    м
    0.70
     в
    0.66
    то
    0.64
    ம்
    0.64
    ین
    0.62
     tropomyosin
    0.60
     giảng
    0.59
     roche
    0.59
     suisse
    0.59
    ру
    0.59
    Activations Density 0.002%

    No Known Activations